mlfoundations-dev/OpenThinker-7B_eval_03-10-25_08-29-49_0981
收藏Hugging Face2025-03-10 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/OpenThinker-7B_eval_03-10-25_08-29-49_0981
下载链接
链接失效反馈官方服务：
资源简介：
这是一个包含OpenThinker-7B模型在不同数学和编码测试集上评估结果的预计算数据集。测试集包括LiveCodeBench、AIME24、AIME25、AMC23、GPQADiamond和MATH500，每个测试集都有多次运行的结果，包括准确率、解决的问题数量和总问题数量。
This is a dataset of precomputed model outputs for evaluating the OpenThinker-7B model on various math and coding benchmarks, including LiveCodeBench, AIME24, AIME25, AMC23, GPQADiamond, and MATH500. Each benchmark has multiple runs with results including accuracy, number of questions solved, and total number of questions.
提供机构：
mlfoundations-dev
